Clinical Semantic Intelligence (CSI): Emulating the Cognitive Framework of the Expert Clinician for Comprehensive Oral Disease Diagnosis

TL;DR

This paper introduces Clinical Semantic Intelligence (CSI), an AI system that emulates expert clinician reasoning to diagnose 118 oral diseases with high accuracy, advancing diagnostic AI beyond pattern matching.

Contribution

The paper presents a novel AI framework combining multimodal models and hierarchical reasoning to emulate expert clinical diagnosis in oral health.

Findings

CSI's Fast Mode achieved 73.4% accuracy.

Standard Mode with HDRT reached 89.5% accuracy.

The hierarchical reasoning significantly improved diagnostic performance.

Abstract

The diagnosis of oral diseases presents a problematic clinical challenge, characterized by a wide spectrum of pathologies with overlapping symptomatology. To address this, we developed Clinical Semantic Intelligence (CSI), a novel artificial intelligence framework that diagnoses 118 different oral diseases by computationally modeling the cognitive processes of an expert clinician. Our core hypothesis is that moving beyond simple pattern matching to emulate expert reasoning is critical to building clinically useful diagnostic aids. CSI's architecture integrates a fine-tuned multimodal CLIP model with a specialized ChatGLM-6B language model. This system executes a Hierarchical Diagnostic Reasoning Tree (HDRT), a structured framework that distills the systematic, multi-step logic of differential diagnosis. The framework operates in two modes: a Fast Mode for rapid screening and a Standard Mode that leverages the full HDRT for an interactive and in-depth diagnostic workup. To train and validate our system, we curated a primary dataset of 4,310 images, supplemented by an external hold-out set of 176 images for final validation. A clinically-informed augmentation strategy expanded our training data to over 30,000 image-text pairs. On a 431-image internal test set, CSI's Fast Mode achieved an accuracy of 73.4%, which increased to 89.5% with the HDRT-driven Standard Mode. The performance gain is directly attributable to the hierarchical reasoning process. Herein, we detail the architectural philosophy, development, and rigorous evaluation of the CSI framework.